Equine Pain Behavior Classification via Self-Supervised Disentangled Pose Representation

TL;DR

This paper introduces a novel self-supervised approach for classifying horse pain from video data, disentangling pose from appearance, and achieving accuracy surpassing human experts using weakly labeled multi-view footage.

Contribution

It presents a new method combining self-supervised disentangled pose representation with multi-instance learning for weakly supervised equine pain classification.

Findings

Achieves 60% pain classification accuracy, surpassing human experts.

Latent horse pose representation is viewpoint covariant and disentangled from appearance.

Qualitative analysis aligns model pain detection with veterinary pain scales.

Abstract

Timely detection of horse pain is important for equine welfare. Horses express pain through their facial and body behavior, but may hide signs of pain from unfamiliar human observers. In addition, collecting visual data with detailed annotation of horse behavior and pain state is both cumbersome and not scalable. Consequently, a pragmatic equine pain classification system would use video of the unobserved horse and weak labels. This paper proposes such a method for equine pain classification by using multi-view surveillance video footage of unobserved horses with induced orthopaedic pain, with temporally sparse video level pain labels. To ensure that pain is learned from horse body language alone, we first train a self-supervised generative model to disentangle horse pose from its appearance and background before using the disentangled horse pose latent representation for pain classification. To make best use of the pain labels, we develop a novel loss that formulates pain classification as a multi-instance learning problem. Our method achieves pain classification accuracy better than human expert performance with 60% accuracy. The learned latent horse pose representation is shown to be viewpoint covariant, and disentangled from horse appearance. Qualitative analysis of pain classified segments shows correspondence between the pain symptoms identified by our model, and equine pain scales used in veterinary practice.